All projects
Multi-AgentDec 2025 – Jan 2026Agentic AI

Zone Scout

Multi-agent lead intelligence system with an automated enrichment layer over Google Maps Places API — verified contacts, reviews, business metadata, and social profiles per validated lead.

Pipeline

Map screenshot/ZIP
Gemini geocoding
Llama audit
Places enrichment
Streamlit UI

The problem

Maps list businesses but do not judge them. Building a qualified local lead list means opening every listing by hand, checking whether it matches your criteria, and hunting for contacts and social profiles separately.

Architecture

End-to-end flow, stage by stage.

  1. 01

    Map screenshot/ZIP

  2. 02

    Gemini geocoding

  3. 03

    Llama audit

  4. 04

    Places enrichment

  5. 05

    Streamlit UI

How it works

01

Zone defined by ZIP or screenshot

A search boundary can be typed as a ZIP code or dropped in as a map screenshot, which Gemini 1.5 Flash reads visually before Google Maps geocoding converts it into a precise geographic zone.

02

Reasoning agent audits every lead

Llama 3.3 70B on Groq reviews each discovered business against the user's stated criteria and rejects the ones that do not qualify, so filtering is a reasoning step rather than a keyword match.

03

Automatic enrichment

Surviving leads gain Places API details, reviews, hours and verified contacts, plus context-aware social links — LinkedIn for tech firms, Instagram for retail — collapsing a multi-hour research task into minutes.

04

Streamlit delivery

The whole flow ships as a Streamlit app with dotenv-managed keys, deployed publicly so it can be tried without setup.

  • Accepted either a ZIP code or map screenshot as the search boundary, using Gemini 1.5 Flash vision plus Google Maps geocoding to translate visual intent into a precise geographic zone.
  • A Llama 3.3 70B reasoning agent on Groq audited discovered businesses against the user's criteria before they entered the result set.
  • Enriched validated leads with Places API details, reviews, hours, contacts, and context-aware social links, turning a multi-hour research task into a minutes-long workflow.

By the numbers

Lead quality lift

Enrichment sources per lead

higher is better
Before
1–2
After
4+

Leads audited automatically (%)

higher is better
Before
Manual
After
100%

Time per zone (minutes)

lower is better
Before
~3 hrs
After
~10 min

What it ships with

  • Multi-agent vision plus reasoning pipeline
  • ZIP code or map screenshot input
  • Criteria-based lead auditing
  • Verified contacts, reviews and hours
  • Category-aware social profile generation
ImpactBefore → After
1-24+
Enrichment sources per lead
ManualZero-touch
Lead validation pipeline

Stack

Llama 3.3 70BGroqGemini 1.5 FlashGoogle Maps APIFastAPIStreamlit